© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 22266
    Prev
    Next
    INDEX
    Explanations

    supply

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å®ı
    -0.27
    wh
    -0.26
    ç»ĵ
    -0.25
     overhead
    -0.24
    ί
    -0.24
    è¡Į
    -0.24
     asserted
    -0.23
     re
    -0.23
     Modular
    -0.23
     bus
    -0.23
    POSITIVE LOGITS
     kald
    0.26
    沸
    0.25
    fluid
    0.25
     oy
    0.25
    _timeline
    0.25
    framework
    0.25
    èĥ½æĬĬ
    0.24
    erland
    0.24
     UPDATED
    0.24
    åij¨äºĮ
    0.24
    Activations Density 0.012%

    No Known Activations